nhaliday + dataviz   42

America's Ur-Choropleths
Gabriel Rossman remarked to me a while ago that most choropleth maps of the U.S. for whatever variable in effect show population density more than anything else. (There’s an xkcd strip about this, too.) The other big variable, in the U.S. case, is Percent Black. Between the two of them, population density and percent black will do a lot to obliterate many a suggestively-patterned map of the United States. Those two variables aren’t explanations of anything in isolation, but if it turns out it’s more useful to know one or both of them instead of the thing you’re plotting, you probably want to reconsider your theory.

https://www.nytimes.com/interactive/2016/12/26/upshot/duck-dynasty-vs-modern-family-television-maps.html
https://www.nytimes.com/interactive/2017/08/07/upshot/music-fandom-maps.html
scitariat  sociology  data  maps  usa  visualization  dataviz  within-group  degrees-of-freedom  roots  regularizer  population  density  race  demographics  things  phalanges  society  multi  news  org:rec  culture  tv  media  politics  american-nations  org:data  urban  polarization  class-warfare  music  urban-rural 
august 2017 by nhaliday
Germ theory of disease - Wikipedia
The germ theory was proposed by Girolamo Fracastoro in 1546, and expanded upon by Marcus von Plenciz in 1762. Such views were held in disdain, however, and Galen's miasma theory remained dominant among scientists and doctors. The nature of this doctrine prevented them from understanding how diseases actually progressed, with predictable consequences. By the early nineteenth century, smallpox vaccination was commonplace in Europe, though doctors were unaware of how it worked or how to extend the principle to other diseases. Similar treatments had been prevalent in India from just before 1000 A.D.[2] [N 1] A transitional period began in the late 1850s as the work of Louis Pasteur and Robert Koch provided convincing evidence; by 1880, miasma theory was struggling to compete with the germ theory of disease. Eventually, a "golden era" of bacteriology ensued, in which the theory quickly led to the identification of the actual organisms that cause many diseases.[3][4] Viruses were discovered in the 1890s.
concept  disease  parasites-microbiome  bio  science  medicine  meta:medicine  spreading  history  iron-age  medieval  early-modern  europe  mediterranean  the-classics  germanic  britain  dataviz  stories  being-right  info-dynamics  discovery  innovation  wiki  reference  the-trenches  public-health  big-peeps  epidemiology  the-great-west-whale 
may 2017 by nhaliday
Charles Joseph Minard - Wikipedia
Charles Minard's map of Napoleon's disastrous Russian campaign of 1812. The graphic is notable for its representation in two dimensions of six types of data: the number of Napoleon's troops; distance; temperature; the latitude and longitude; direction of travel; and location relative to specific dates.[2]
people  history  early-modern  europe  gallic  war  russia  dataviz  visualization  wiki  maps  stock-flow  military  classic 
april 2017 by nhaliday
Why does 'everything look correlated on a log-log scale'? - Quora
A correlation on a log log scale is meant to suggest the data follows a power law relationship of the form yy∝x−n.∝x−n.

A low R2R2 is suppose to suggest that the data either actually follows some other distribution like yy∝e−x∝e−xor is simply random noise. The problem is that log log correlation is a necessary but not sufficient condition to prove a power law relationship. While ruling out random noise is fairly easy, ruling out an alternate functional form is much harder- you can reject a power law hypothesis by a log log plot but you cannot prove it by one. As Aaron Brown answer points out, a lot of stuff that looks like it has a power law relationship does not actually follow it in reality. In particular, an exponential or log normal relationship might give similar results over most of the range but will diverge strongly at the tail end .[1] This difference can be difficult to detect if limited data is collected at the tail ends and deviations look like noise.

An example of a log normal distribution plotted on a normal and log-log scale. [2] Note the appearance of a straight line on the right tail that diverges strongly on the left tail. Using a power law relationship in this region will cause serious errors.
q-n-a  qra  data-science  correlation  regression  magnitude  dataviz  street-fighting  gotchas  nibble  plots  multiplicative  additive  power-law 
february 2017 by nhaliday
Why xkcd-style graphs are important - Chris Stucchio
A: lowering expectations
and apparently matplotlib has this visualization built-in
rhetoric  dataviz  libraries  python  howto  techtariat 
november 2016 by nhaliday
In Investing, It’s When You Start and When You Finish (2011) | Hacker News
The Best Investment Since 1926? Apple: https://www.nytimes.com/2017/09/22/business/apple-investment.html
That conclusion emerges from a study of stock market returns by Hendrik Bessembinder, a finance professor at the W. P. Carey School of Business at Arizona State University. His broad findings on the market are startling: Most stocks aren’t good investments. They don’t even beat the paltry returns of one-month Treasury bills, he has found.

But a relative handful of stocks are extraordinary performers. Only 4 percent of all publicly traded stocks account for all of the net wealth earned by investors in the stock market since 1926, he has found. A mere 30 stocks account for 30 percent of the net wealth generated by stocks in that long period, and 50 stocks account for 40 percent of the net wealth.
commentary  hn  finance  investing  data  visualization  news  org:rec  dataviz  personal-finance  nitty-gritty  securities  multi  analysis  study  summary  uncertainty  winner-take-all  outcome-risk  moments  top-n  apple  money 
october 2016 by nhaliday
Tax Day: Are You Receiving a Marriage Penalty or Bonus? - The New York Times
When countries design their tax systems, they have to make some choices. Here are three possible goals:
- Higher-income people pay higher tax rates than lower-income people.
- Married couples who earn the same amount of money pay the same amount in taxes, no matter who earns the money.
- Taxes don’t depend on whether couples are married.

It’s not possible to achieve all three goals at the same time. Most wealthy countries give up on the second goal, favoring couples with two earners over couples with only one. The United States gives up on the third.
personal-finance  policy  visualization  data  government  data-science  news  usa  org:rec  org:data  taxes  trivia  wonkish  class  compensation  dataviz  analysis  incentives  life-history  money 
april 2016 by nhaliday

bundles : engframetechie

related tags

2016-election  abstraction  acm  acmtariat  additive  advice  age-generation  algorithms  american-nations  analysis  anglo  anglosphere  antiquity  apple  aristos  article  asia  backup  being-right  benchmarks  best-practices  better-explained  big-peeps  big-picture  bio  blog  brexit  britain  broad-econ  cause  cheatsheet  checking  checklists  china  civilization  class  class-warfare  classic  coalitions  commentary  comparison  compensation  composition-decomposition  compression  concentration-of-measure  concept  confidence  cool  correlation  counterexample  critique  crosstab  culture  culture-war  curiosity  current-events  d3  data  data-science  database  dataviz  debugging  deep-learning  degrees-of-freedom  demographics  density  design  developing-world  devtools  discovery  discussion  disease  documentation  duplication  dynamic  early-modern  econ-metrics  econometrics  economics  education  elections  elegance  engineering  ensembles  epidemiology  epistemic  error  essay  EU  europe  examples  expectancy  expert-experience  explanation  exploratory  exposition  finance  frameworks  gallic  gelman  gender  generalization  germanic  google  gotchas  government  gradient-descent  graph-theory  graphs  great-powers  growth-econ  guide  hci  health  history  hmm  hn  homepage  homo-hetero  howto  hypothesis-testing  incentives  india  industrial-revolution  info-dynamics  info-foraging  init  innovation  insight  interpretability  intersection  intersection-connectedness  intricacy  investing  iron-age  japan  javascript  journos-pundits  language  latin-america  left-wing  len:short  let-me-see  letters  libraries  life-history  linearity  list  lived-experience  machine-learning  macro  magnitude  maps  measure  media  medicine  medieval  mediterranean  mental-math  meta:medicine  methodology  metrics  military  mit  models  moments  money  mostly-modern  multi  multiplicative  music  news  nibble  nitty-gritty  nonlinearity  obesity  objektbuch  occam  oly  oly-programming  operational  optimization  org:anglo  org:biz  org:bleg  org:data  org:davos  org:edu  org:junk  org:lite  org:nat  org:rec  org:sci  organization  oss  outcome-risk  overflow  parasites-microbiome  parsimony  pdf  people  personal-finance  phalanges  pic  plots  polarization  policy  polisci  politics  poll  population  power-law  pre-2013  pre-ww2  pro-rata  profile  programming  psychology  public-health  python  q-n-a  qra  race  random  rant  rat-pack  rationality  ratty  recommendations  reference  regional-scatter-plots  regression  regularization  regularizer  replication  rhetoric  rock  roots  russia  scale  science  scitariat  securities  sequential  sinosphere  skunkworks  social  society  sociology  software  spreading  ssc  stackex  startups  stats  stock-flow  stories  stream  street-fighting  study  summary  taxes  techtariat  terminal  the-classics  the-great-west-whale  the-trenches  things  thinking  time  time-series  tip-of-tongue  tools  top-n  toxoplasmosis  track-record  trends  tribalism  trivia  trump  tutorial  tv  twitter  ui  unaffiliated  uncertainty  unsupervised  urban  urban-rural  usa  via:popular  video  visual-understanding  visualization  vulgar  war  wealth  wealth-of-nations  web  wiki  winner-take-all  within-group  wonkish  world  worrydream  yak-shaving  yvain  🎩 

Copy this bookmark:



description:


tags: